google-research/pegasus

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1655 stars · 318 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PEGASUS is Google Research's implementation of transformer encoder-decoder models pre-trained with the Gap Sentences Generation objective for abstractive text summarization. It includes pre-trained checkpoints, a Flax-based PEGASUS-X variant, and training/evaluation code.

Use cases

• summarize long documents into short abstracts
• fine-tune a pre-trained summarization model on my own dataset
• train a sequence-to-sequence model with gap sentence pre-training
• evaluate summarization models with ROUGE on benchmark datasets
• use PEGASUS-X for long-input summarization
• download pre-trained summarization checkpoints for research

When to choose

• you need state-of-the-art abstractive summarization models with published benchmarks
• you want to reproduce or extend the PEGASUS/PEGASUS-X research
• you need pre-trained checkpoints for fine-tuning on custom summarization data

When to avoid

• you need a production summarization API rather than research code
• you want a maintained library with frequent updates - the repo is largely in maintenance mode
• you need general-purpose text generation beyond summarization

Facets

library · maturity maintenance

machine-learning deep-learning nlp transformers llm-training machine-learning deep-learning python cloud abstractive-summarization sequence-to-sequence pretraining flax tensorflow research-models text-summarization natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-research/pegasus")